Image quality assessment using edge based features

Attar, Rahman and Shahbahrami, Asadollah and Rad, Reza Moradi (2016) Image quality assessment using edge based features. Multimedia Tools and Applications, 75 (12). pp. 7407-7422. ISSN 1380-7501

Full content URL: http://link.springer.com/article/10.1007/s11042-01...

Documents
Image quality assessment using edge based features

Request a copy
[img] PDF
art%3A10.1007%2Fs11042-015-2663-9.pdf - Whole Document
Restricted to Repository staff only

1MB
Item Type:Article
Item Status:Live Archive

Abstract

There are many applications for Image Quality Assessment (IQA) in digital image processing. Many techniques have been proposed to measure the quality of an image such as Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Mean Structural Similarity Index Measurement (MSSIM). In this paper, a new technique, namely, Edge Based Image Quality Assessments (EBIQA) is proposed. The proposed technique is based on different edge features which are extracted from original (distortion free) and distorted images. The new approach was implemented and tested using different images which have been taken from A57 and WIQ image databases. The experimental results show that the functionality of the EBIQA technique is better than the state of art IQA techniques. The proposed technique is consistent with the mean opinion score which makes it suitable for automatic image quality assessment. © 2015 Springer Science+Business Media New York

Keywords:Image quality, Signal to noise ratio, Edge-based, Full references, Image quality assessment, Image quality assessment (IQA), Mean opinion scores, Mean structural similarity indices, Peak signal to noise ratio, Structural similarity, Image processing, JCNotOpen
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G450 Multi-media Computing Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:17749
Deposited On:24 Jul 2015 09:40

Repository Staff Only: item control page